To cope with real-world dynamics, an intelligent system needs to incrementally acquire,
update, accumulate, and exploit knowledge throughout its lifetime. This ability, known as …

The remarkable performance of deep Convolutional neural networks (CNNs) is generally
attributed to their deeper and wider architectures, which can come with significant …

We present ControlNet, a neural network architecture to add spatial conditioning controls to
large, pretrained text-to-image diffusion models. ControlNet locks the production-ready large …

Learning is highly important for edge intelligence devices to adapt to different application
scenes and owners. Current technologies for training neural networks require moving …

Continual learning can empower vision-language models to continuously acquire new
knowledge without the need for access to the entire historical dataset. However mitigating …

Continual learning aims to enable a single model to learn a sequence of tasks without
catastrophic forgetting. Top-performing methods usually require a rehearsal buffer to store …

Federated learning has emerged as an important distributed learning paradigm, which
normally involves collaborative updating with others and local updating on private data …

The mainstream paradigm behind continual learning has been to adapt the model
parameters to non-stationary data distributions, where catastrophic forgetting is the central …

Task arithmetic has recently emerged as a cost-effective and scalable approach to edit pre-
trained models directly in weight space: By adding the fine-tuned weights of different tasks …

The last decade of machine learning has seen drastic increases in scale and capabilities.
Deep neural networks (DNNs) are increasingly being deployed in the real world. However …